Hacktoberfest 2026:メンテナが10月に向けて印を付けた、オープンで初心者向けの issue。 Hacktoberfest の issue を見る

no_rope_layer_interval is declared but never applied, and SmolLM3's own config sets it

オープン
#22,043 コメント 2 件 リアクション 0 件 担当者 2 名 GitHub で見る

メンテナーはふだん 1 日以内に返信

@MukeshK17 がすでに取り組んでいます。

2026年8月24日 から。

  • #22177 @MukeshK17 による — オープン

評価

この issue はまだ評価されていません。

説明

module: llm triaged

ModelArgs declares no_rope_layer_interval, and examples/models/smollm3/3b_config.json sets it to 4, but nothing on the examples/models/llama export path reads it. On main (e4576d0) the name appears exactly once across the 32 Python files of that path:

examples/models/llama/model_args.py:119:    no_rope_layer_interval: Optional[int] = (

__post_init__ does not touch it, and Attention.forward applies rope unconditionally (attention.py:529, attention.py:563) with no layer-index test. The two places that do honour it are backends/mlx/llm/et_attention.py:111 and examples/qualcomm/oss_scripts/llama/model/static_llama.py:288.

So a model that alternates RoPE and NoPE layers exports without complaint and comes out with rope on every layer.

Reproducing

examples/models/smollm3/3b_config.json and examples/models/smollm3/convert_weights.py are both in the tree, so SmolLM3-3B looks ready to export. Converting its weights and exporting through export_llm with that params json (XNNPACK, 8da4w + 8-bit embedding, 1852.2 MB) gives a .pte that loads and runs, then does this:

prompt: <|im_start|>user\nWhat is the capital of France?<|im_end|>\n<|im_start|>assistant\n
output: Okay, so you want to know what what what what what what what what what what what
        what what what what what what what what what what what what what what what what

prompt: <|im_start|>user\nWhat is 17 times 4?<|im_end|>\n<|im_start|>assistant\n
output: I think you are looking for an answer that can be given that can be be be be be
        determ determ determ determ determ determ determ determ determ determ#ae determ#

It starts as English and collapses, which is what a positional-encoding mismatch looks like: the first few tokens are fine and the drift grows with position.

What would help

Either implement the interval on this path, or reject a params json that sets a field the chosen backend does not implement. The silent version is the expensive one — the export succeeds, the file is the right size, and the model is simply a different model.

Measured with the executorch 1.4.0 wheel; the code paths quoted above are byte-identical on main at e4576d0.

cc @larryliu0820 @mergennachin @cccclai @helunwencser @jackzhxng @digantdesai

主要言語
Python
スター
5.1k
フォーク
1.2k
平均マージ
2日 9時間
マージ済み PR(30日)
661

環境構築

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

pytorch/executorch のほかの issue

pytorch/executorch の issue をすべて見る

似ている issue

Python の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。